Online Depth Image-Based Object Tracking with Sparse Representation and Object Detection

摘要

Online object tracking under complex environments is an important but challenging problem in computer vision, especially for illumination changing and occlusion conditions. With the emergence of commercial real-time depth cameras like Kinect, depth image-based object tracking, which is insensitive to illumination changing, gains more and more attentions. In this paper, we propose an online depth image-based object tracking method with sparse representation and object detection. In this framework, we combine tracking and detection to leverage precision and efficiency under heavy occlusion conditions. For tracking, objects are represented by sparse representations learned online with update. For detection, we apply two different strategies based on tracking-learning-detection and wider search window approaches. We evaluate our methods on both the subset of the public dataset Princeton Tracking Benchmark and our own driver face video in a simulated driving environment. The quantitative evaluations of precision and running time on these two datasets demonstrate the effectiveness and efficiency of our proposed object tracking algorithms.